start_conversation

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It doesn't state whether this starts a new thread only, whether it can reply to existing conversations, what happens if a conversation already exists with the target person, or whether actions are reversible. For a mutation tool (sending a message to a real person) with zero annotation coverage, this is a significant gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Single concise sentence that effectively states the action and target. Zero wasted words. The brevity is a strength here, though it comes at the cost of missing guidance details.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool that sends real LinkedIn messages (irreversible external action) with no annotations and no output schema, this is under-specified. Missing: what dry_run does, message length constraints, whether it appends to existing threads, login requirements, and how errors/duplicate conversations are handled. The 'dry_run' parameter especially needs documentation since it has no schema description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 33% (only 'profile' has a description in the schema). The description explains 'profile' (URL or vanity name) but does not explain the 'message' parameter requirements or the 'dry_run' parameter at all. dry_run in particular is a non-obvious parameter (likely a test mode) that needs explanation and receives none.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('Start') with a clear resource ('new LinkedIn message to a person') and method of identification (profile URL or vanity name). It's clear on the action, though it doesn't explicitly differentiate from the sibling 'send_message' tool, which appears to be a close alternative. Slightly unclear how it differs from send_message.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool vs. the sibling 'send_message' tool, which appears semantically similar. No context about prerequisites like being logged in (though there's a linkedin_login sibling), no indication of message length limits or other constraints. The when-to-use context is entirely absent.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.